Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    positive expressions of satisfaction and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    works well

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sin
    -0.29
     potencial
    -0.28
     recha
    -0.27
     piatti
    -0.27
     special
    -0.25
     backs
    -0.25
     rivals
    -0.24
    Uhr
    -0.24
    -
    -0.24
     jewellery
    -0.23
    POSITIVE LOGITS
    ArgumentParser
    0.84
    MigrationBuilder
    0.75
    ftagPool
    0.73
    ConstraintMaker
    0.73
    RegressionTest
    0.68
    findpost
    0.67
    存于互联网档案馆
    0.66
     protoimpl
    0.63
    UserScript
    0.63
    цездатний
    0.62
    Act Density 0.104%

    No Known Activations